Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 850 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2838. Min Act: -0.0000

Data Index: 144412 (C4 (Web Text))

Max Activating Token Index: 779

Text #1

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2506. Min Act: -0.0001

Data Index: 441873 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2754. Min Act: -0.0000

Data Index: 91111 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2592. Min Act: -0.0001

Data Index: 467008 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2652. Min Act: -0.0001

Data Index: 1341297 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2359. Min Act: -0.0001

Data Index: 167184 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2535. Min Act: -0.0001

Data Index: 1199592 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2327. Min Act: -0.0000

Data Index: 723081 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2299. Min Act: -0.0000

Data Index: 925776 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2333. Min Act: -0.0001

Data Index: 452376 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2218. Min Act: -0.0001

Data Index: 889898 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2107. Min Act: -0.0001

Data Index: 1299048 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2215. Min Act: -0.0001

Data Index: 1246470 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2234. Min Act: -0.0001

Data Index: 182167 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2056. Min Act: -0.0001

Data Index: 1181442 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2273. Min Act: -0.0000

Data Index: 739053 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2184. Min Act: -0.0000

Data Index: 370913 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2014. Min Act: -0.0001

Data Index: 959136 (C4 (Web Text))

Max Activating Token Index: 540

Text #18

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2011. Min Act: -0.0001

Data Index: 341696 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2403. Min Act: -0.0001

Data Index: 1074475 (C4 (Web Text))

Max Activating Token Index: 924